Accurate single image super‐resolution using cascading dense connections. Issue 13 (1st June 2019)

• Record Type: Journal Article
• Authors: Wei, Wei; Feng, Guoqi; Zhang, Qi; Cui, Dongliang; Zhang, Miao; Chen, Feng
• Is Part Of: Electronics letters. Volume 55:Issue 13(2019)
• Page Start: 739
• Page End: 742
• Publication Date: 2019-06-01
• Subjects: object recognition -- learning (artificial intelligence) -- image resolution -- neural nets -- convolution; cascading dense connection -- CDN -- deep network -- accurate single image super‐resolution -- deep learning methods -- deep convolutional neural network -- single‐image super‐resolution task -- accurate SISR method -- cascading dense network -- cascading mechanism -- dense connected convolutional layers; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2019.0392
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : In recent years, deep learning methods, especially deep convolutional neural network, have been successfully applied to the single‐image super‐resolution (SISR) task. In this Letter, the authors propose an accurate SISR method by introducing cascading dense connections in a very deep network. In detail, they construct the cascading dense network (CDN) to fully make use of the hierarchical features from all the convolutional layers, which implements a cascading mechanism upon the dense connected convolutional layers. The cascading dense connection in the CDN enables short and long paths to be built directly from the output to each layer, alleviating the vanishing‐gradient problem of very deep networks. Extensive experiments show that CDN achieves state‐of‐the‐art performance on traditional metrics (PSNR and SSIM). Also, they introduce object recognition as the additional evaluation metric for SISR, which further demonstrates the effectiveness of the authors' method.